arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01586cs.CV
收藏

HandMCM:基于多模态点云的对应状态空间模型用于3D手姿态估计

HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation

Wencan Cheng, Gim Hee Lee

AI总结:

本文提出HandMCM,通过结合局部信息注入/过滤模块和对应建模,利用状态空间模型提升3D手姿态估计的鲁棒性和精度,实验表明其在严重遮挡场景中优于现有方法。

摘要:

3D手姿态估计对于许多人机交互应用如增强现实至关重要。然而,由于手部自遮挡和与物体的相互作用导致的遮挡,该任务面临重大挑战。本文提出HandMCM,基于强大的状态空间模型(Mamba),通过整合局部信息注入/过滤模块和对应建模,有效学习了各种遮挡场景下的高动态关节点拓扑结构。此外,通过整合多模态图像特征,增强了输入的鲁棒性和表征能力,从而实现了更准确的手部姿态估计。在三个基准数据集上的实验证明,我们的模型在严重遮挡的挑战性场景中显著优于现有最先进方法。这些结果突显了我们方法在实际应用中提升3D手姿态估计准确性和可靠性的潜力。

英文摘要:

3D hand pose estimation that involves accurate estimation of 3D human hand keypoint locations is crucial for many human-computer interaction applications such as augmented reality. However, this task poses significant challenges due to self-occlusion of the hands and occlusions caused by interactions with objects. In this paper, we propose HandMCM to address these challenges. Our HandMCM is a novel method based on the powerful state space model (Mamba). By incorporating modules for local information injection/filtering and correspondence modeling, the proposed correspondence Mamba effectively learns the highly dynamic kinematic topology of keypoints across various occlusion scenarios. Moreover, by integrating multi-modal image features, we enhance the robustness and representational capacity of the input, leading to more accurate hand pose estimation. Empirical evaluations on three benchmark datasets demonstrate that our model significantly outperforms current state-of-the-art methods, particularly in challenging scenarios involving severe occlusions. These results highlight the potential of our approach to advance the accuracy and reliability of 3D hand pose estimation in practical applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑